agentsclimarketplace

Lemma mcp

Skill uselemma/lemma/skills/lemma-mcp

Drive the Lemma MCP from the terminal. Use when the user asks about Lemma issues, agent failures, incidents, or regressions; wants to review, validate, confirm, dismiss, fix, or resolve detections; or asks questions like "are there issues where users get frustrated", "any urgent lemma issues", "look through all urgent issues and validate each", or "dismiss everything under X impact." Also use when browsing, ranking, or acting on Lemma detections over MCP.From its SKILL.md

Install
npx -y skills add uselemma/lemma --skill lemma-mcp

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 5 stars5 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.7 KB, as published. Nobody here has run it

Lemma MCP

You are driving the Lemma MCP. Lemma detects semantic failures in production AI agents. Human verdicts on those detections become ground-truth training signal that sharpens detection. That is why the rules below are strict about who decides.

Core rules

  1. Reads run freely. Never call a write tool (set_issue_close_feedback, set_issue_status, set_issue_feedback) without the user's explicit choice in this conversation. Propose verdicts; never write them on your own judgment.
  2. Skip records nothing. Confirm, dismiss, and resolve always write back.
  3. Never show the user a raw UUID or raw JSON. Render issues as an 8-char id prefix plus a list ordinal, e.g. [2] a3f81c92. Resolve references like "the second one" yourself.
  4. Copy style in everything you render: sentence case, terse, no em-dashes.

Workflows

AreaWhenReference
IssuesTriage detections: list, rank, drill into evidence, confirm / dismiss / resolvereferences/issues.md

Read the matching reference before acting. Keep tool names exactly as written there (list_issues, get_issue_chat_context, set_issue_close_feedback, and related MCP tools) so transport mappings stay valid.

Keep looking

Skills are one crate of 627,801. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.